In this paper, nearest neighbor prediction is used to decide Pareto dominance of candidate solutions in expensive multi-objective optimization. For improving the accuracy of predicting Pareto dominance in decision space, a transformation method of decision space is proposed. Based on correlation analysis of objective functions and decision attributes, computationally efficient attribute tendency models of objective functions are set up. These models are used to re-construct the decision space such that the ...
引用格式李文彬,贺建军,冯彩英,郭观七.基于决策空间变换最近邻方法的Pareto支配性预测.自动化学报,2017,43(2):294-301Prediction of Pareto Dominance Using Nearest Neighbor Method Based onDecision Space TransformationLI Wen-Bin1,2HE Jian-Jun1FENG Cai-Ying2进化算法